{"total":169,"rows":[{"id":"2403.15388","title":"LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models","created":"2024-03-22","cited_by_count":402,"area":"lr"},{"id":"2403.07378","title":"SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression","created":"2024-03-12","cited_by_count":243,"area":null},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2411.05007","title":"SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models","created":"2024-11-07","cited_by_count":170,"area":"diffusion"},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2405.17430","title":"Matryoshka Multimodal Models","created":"2024-05-27","cited_by_count":84,"area":"mllm"},{"id":"2405.16005","title":"PTQ4DiT: Post-training Quantization for Diffusion Transformers","created":"2024-05-25","cited_by_count":79,"area":"diffusion"},{"id":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"id":"2411.01016","title":"MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition","created":"2024-11-01","cited_by_count":57,"area":"moe"},{"id":"2411.01433","title":"HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference","created":"2024-11-03","cited_by_count":55,"area":"moe"},{"id":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"area":null},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"id":"2406.05223","title":"CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning","created":"2024-06-07","cited_by_count":44,"area":null},{"id":"2406.14909","title":"Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths","created":"2024-06-21","cited_by_count":44,"area":null},{"id":"2412.14363","title":"ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals","created":"2024-12-18","cited_by_count":36,"area":null},{"id":"2410.03765","title":"Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression","created":"2024-10-02","cited_by_count":35,"area":null},{"id":"2502.00425","title":"MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization","created":"2025-02-01","cited_by_count":35,"area":"mllm"},{"id":"2502.17298","title":"Delta Decompression for MoE-based LLMs Compression","created":"2025-02-24","cited_by_count":33,"area":"moe"},{"id":"2410.03129","title":"ARB-LLM: Alternating Refined Binarizations for Large Language Models","created":"2024-10-04","cited_by_count":31,"area":null},{"id":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2410.14731","title":"MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection","created":"2024-10-16","cited_by_count":29,"area":"inference"},{"id":"2407.11239","title":"From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2405.17849","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2501.15296","title":"You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning","created":"2025-01-25","cited_by_count":17,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2505.24357","title":"ReCalKV: Low-Rank KV Cache Compression via Head Reordering and Offline Calibration","created":"2025-05-30","cited_by_count":16,"area":"inference"},{"id":"2510.16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","created":"2025-10-18","cited_by_count":16,"area":"mllm"},{"id":"2410.05437","title":"ESPACE: Dimensionality Reduction of Activations for Model Compression","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2410.17711","title":"Beware of Calibration Data for Pruning Large Language Models","created":"2024-10-23","cited_by_count":15,"area":null},{"id":"2505.20925","title":"Multi-objective Large Language Model Alignment with Hierarchical Experts","created":"2025-05-27","cited_by_count":13,"area":"alignment"},{"id":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2505.05829","title":"Accelerating Diffusion Transformer via Increment-Calibrated Caching with Channel-Aware Singular Value Decomposition","created":"2025-05-09","cited_by_count":12,"area":"diffusion"},{"id":"2510.03274","title":"Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models","created":"2025-09-27","cited_by_count":12,"area":null},{"id":"2602.03051","title":"SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression","created":"2026-02-03","cited_by_count":12,"area":"mechinterp"},{"id":"2409.12963","title":"Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner","created":"2024-09-19","cited_by_count":11,"area":null},{"id":"2506.13771","title":"LittleBit: Ultra Low-Bit Quantization via Latent Factorization","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2510.24273","title":"SALS: Sparse Attention in Latent Space for KV cache Compression","created":"2025-10-28","cited_by_count":11,"area":"inference"},{"id":"2602.00135","title":"LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models","created":"2026-01-28","cited_by_count":11,"area":"mllm"},{"id":"2512.05916","title":"KQ-SVD: Compressing the KV Cache with Provable Guarantees on Attention Fidelity","created":"2025-12-05","cited_by_count":10,"area":"inference"},{"id":"2602.01053","title":"LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents","created":"2026-02-01","cited_by_count":10,"area":"agents"},{"id":"2510.14301","title":"A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space","created":"2025-10-16","cited_by_count":9,"area":"alignment"},{"id":"2605.17757","title":"OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization","created":"2026-05-18","cited_by_count":9,"area":"inference"},{"id":"2412.06071","title":"KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models","created":"2024-12-08","cited_by_count":8,"area":null},{"id":"2504.02658","title":"MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators","created":"2025-04-03","cited_by_count":8,"area":"moe"},{"id":"2505.12942","title":"A3 : an Analytical Low-Rank Approximation Framework for Attention","created":"2025-05-19","cited_by_count":8,"area":"inference"},{"id":"2505.17974","title":"Generalized Fisher-Weighted SVD: Scalable Kronecker-Factored Fisher Approximation for Compressing Large Language Models","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2505.18502","title":"Knowledge Fusion of Large Language Models Via Modular SkillPacks","created":"2025-05-24","cited_by_count":8,"area":null},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2602.02848","title":"Zero Sum SVD: Balancing Loss Sensitivity for Low Rank LLM Compression","created":"2026-02-02","cited_by_count":8,"area":null},{"id":"2410.21271","title":"EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation","created":"2024-10-28","cited_by_count":7,"area":null},{"id":"2412.20185","title":"DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization","created":"2024-12-28","cited_by_count":7,"area":null},{"id":"2505.18413","title":"LatentLLM: Attention-Aware Joint Tensor Compression","created":"2025-05-23","cited_by_count":7,"area":"mllm"},{"id":"2505.20112","title":"ERC-SVD: Error-Controlled SVD for Large Language Model Compression","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2505.22913","title":"Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference","created":"2025-05-28","cited_by_count":7,"area":"inference"},{"id":"2604.02119","title":"AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression","created":"2026-04-02","cited_by_count":7,"area":null},{"id":"2406.16893","title":"A Survey of Transformer-based Language Models with Focus on Efficiency","created":"2024-05-15","cited_by_count":6,"area":null},{"id":"2505.05215","title":"Diffusion Model Quantization: A Review","created":"2025-05-08","cited_by_count":6,"area":"diffusion"},{"id":"2509.22075","title":"CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2512.03383","title":"UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2602.04852","title":"On State Reduction in Linear Attention","created":"2026-02-04","cited_by_count":6,"area":null},{"id":"2502.01705","title":"Progressive Binarization with Semi-Structured Pruning for LLMs","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2502.09003","title":"RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2503.05936","title":"CASP: Compression of Large Multimodal Models Based on Attention Sparsity","created":"2025-03-07","cited_by_count":5,"area":"mllm"},{"id":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2505.05086","title":"Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning","created":"2025-05-08","cited_by_count":5,"area":null},{"id":"2507.07580","title":"COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2603.17946","title":"CARE: Covariance-Aware and Rank-Enhanced Decomposition for Enabling Multi-Head Latent Attention","created":"2026-03-18","cited_by_count":5,"area":"inference"},{"id":"2501.19090","title":"Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models","created":"2025-01-31","cited_by_count":4,"area":null},{"id":"2503.04704","title":"Universality of Layer-Level Entropy-Weighted Quantization Beyond Model Architecture and Size","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2505.20132","title":"Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2506.13187","title":"Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2603.03597","title":"NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training","created":"2026-03-04","cited_by_count":4,"area":null},{"id":"2604.00821","title":"Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation","created":"2026-04-01","cited_by_count":4,"area":null},{"id":"2411.09816","title":"Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition","created":"2024-11-14","cited_by_count":3,"area":null},{"id":"2502.01717","title":"Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2505.18350","title":"How Many Parameters Does Your Task Really Need? Task Specific Pruning with LLM-Sieve","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2505.18451","title":"$\\mu$-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts","created":"2025-05-24","cited_by_count":3,"area":"moe"},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2510.14697","title":"Purifying Task Vectors in Knowledge-Aware Subspace for Model Merging","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2510.19389","title":"ARA: Adaptive Rank Allocation for Efficient Large Language Model SVD Compression","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2512.01980","title":"Low-Rank Prehab: Preparing Neural Networks for SVD Compression","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2512.03062","title":"Globally optimized SVD compression of LLMs via Fermi-function-based rank selection and gauge fixing","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2601.21686","title":"Don't be so Stief! Learning KV Cache low-rank approximation over the Stiefel manifold","created":"2026-01-29","cited_by_count":3,"area":"inference"},{"id":"2604.02570","title":"WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models","created":"2026-04-02","cited_by_count":3,"area":"mllm"},{"id":"2604.03298","title":"ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs","created":"2026-03-28","cited_by_count":3,"area":null},{"id":"2605.08314","title":"FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast","created":"2026-05-08","cited_by_count":3,"area":"inference"},{"id":"2408.11855","title":"FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models","created":"2024-08-15","cited_by_count":2,"area":"moe"},{"id":"2509.23472","title":"Memory-Efficient Fine-Tuning via Low-Rank Activation Compression","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2510.05064","title":"Boomerang Distillation Enables Zero-Shot Model Size Interpolation","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2512.17720","title":"Mitigating Forgetting in Low Rank Adaptation","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2602.02680","title":"FlexRank: Nested Low-Rank Knowledge Decomposition for Adaptive Model Deployment","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.11008","title":"ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2604.01609","title":"Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression","created":"2026-04-02","cited_by_count":2,"area":"inference"},{"id":"2605.10793","title":"ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2608.08506","title":"Understanding Calibration and Truncation Error Propagation in Training-Free Low-Rank Compression for LLMs","created":"2026-08-09","cited_by_count":2,"area":null},{"id":"2405.15877","title":"Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2501.05017","title":"Continuous Knowledge-Preserving Decomposition with Adaptive Layer Selection for Few-Shot Class-Incremental Learning","created":"2025-01-09","cited_by_count":1,"area":null},{"id":"2501.16322","title":"Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture","created":"2025-01-27","cited_by_count":1,"area":null}],"next_cursor":"100"}